Systems and methods for engaging an audience in a conversational advertisement

• US 9,619,812 B2
• Filed: 08/28/2012
• Issued: 04/11/2017
• Est. Priority Date: 08/28/2012
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Balasubramanian, Sundar, McSherry, Michael, Sheedy, Aaron
• Primary Examiner(s): JACKSON, JAKIEDA R
• Application Number:
  US13/597,017
• Publication Number:
  US 20140067395A1
• Time in Patent Office: 1,687 Days
• Field of Search: 704251
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0241 Advertisements
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 25/51 for comparison or discrimination

Abstract

A system and method are described for engaging an audience in a conversational advertisement. A conversational advertising system converses with an audience using spoken words. The conversational advertising system uses a speech recognition application to convert an audience'"'"'s spoken input into text and a text-to-speech application to transform text of a response to speech that is to be played to the audience. The conversational adverting system follows an advertisement script to guide the audience in a conversation.

Claims

1. A system for engaging an audience in a conversational advertisement, wherein the system includes a processor and a memory, the system comprising:

a conversation module implemented by the processor and configured to;

receive an indication to present a conversational advertisement to multiple members of an audience;

identify a conversational advertisement to present to the multiple members of the audience;

convey a first message of the conversational advertisement to the multiple members of the audience,

wherein the first message is conveyed contemporaneously to the multiple members using a single communication session;

process spoken words from audio data representing a verbal response to the first message from a first member of the multiple members of the audience,

wherein the verbal response to the first message is one of multiple individual responses provided by two or more of the multiple members of the audience; and

determine a response to convey to the first member of the audience,

wherein the response to convey to the first member of the audience is determined based at least in part on the spoken words from the audio data representing the verbal response to the first message from the first member of the audience; and

a speech recognition module implemented by the processor and configured to;

receive audio data representing the verbal response of the first member of the audience to the first message of the conversational advertisement; and

identify spoken words from the audio data representing the verbal response to the first message from the first member of the audience.

2. The system of claim 1:

wherein the conversational advertisement includes an advertisement script, wherein the advertisement script includes multiple possible responses based on different received verbal responses; and

wherein the conversation module is further configured to;

compare (A) the spoken words from the audio data representing the verbal response to the first message to (B) at least a portion of the advertisement script, and

identify, based on the comparison, a script response that is included in the advertisement script as the response to convey to the member of the audience.

3. The system of claim 1,

wherein the response to convey to the first member of the audience is based on identified information associated with the first member of the audience;

wherein the information associated with the first member of the audience includes gender information determined by analyzing the audio data representing the verbal response to the first message.

4. The system of claim 1, wherein the conversation module is further configured to identify a conversational advertisement to present to the multiple members of the audience based at least in part on information associated with one or more of the multiple members of the audience.

5. The system of claim 1, wherein the conversational advertisement includes an advertisement script that includes at least one of:

a non-connected path configured to be used to navigate the advertisement script when the audio data representing the verbal response to the first message from the first member of the audience cannot be received,

a nonsense path configured to be used to navigate the advertisement script when the audio data representing the verbal response to the first message from the first member of the audience is nonsensical,

a default path configured to be used to navigate the advertisement script when, despite being able to receive audio data, no audio data representing the verbal response to the first message from the first member of the audience is received, or

any combination thereof.

6. The system of claim 1, wherein the conversation module is further configured to determine an action that is to be taken based at least in part on the spoken words from the audio data representing the verbal response to the first message from the first member of the audience.

7. The system of claim 1,

wherein the conversational advertisement is presented to the member of the audience through one or more web browsers;

wherein the first message of the conversational advertisement is presented on a first webpage; and

wherein the response to convey to the member of the audience is presented on a second webpage different from the first webpage such that the response to convey to the member of the audience continues the conversational advertisement on the second webpage, picking up from where the member of the audience left off with initial interactions with the conversational advertisement presented on the first webpage.

8. The system of claim 1,

wherein the response to convey to the first member of the audience is further based on a conversation observed between the multiple members of the audience.

9. A method of engaging an audience in a conversational advertisement, wherein the method is performed by a computing system having a processor and a memory, the method comprising:

identifying, at a server computer, a conversational advertisement to present to an audience via a client device in response to a received indication to present an advertisement,

wherein the conversational advertisement is selected from multiple conversational advertisements and

wherein the identified conversational advertisement provides a verbal interface such that the identified conversational advertisement provides responses, to verbal input provided to the verbal interface, that are based on an identified meaning of the verbal input to the verbal interface;

orchestrating, through a first webpage, at least two initial interactions between the audience and the conversational advertisement, wherein one of the at least two initial interactions comprises;

conveying, at the server computer, a first message of the conversational advertisement to the client device to be presented to the audience; and

receiving, at the server computer, audio data from the client device representing a verbal response by the audience to the first message of the conversational advertisement,

wherein the audio data is received through the member of the audience interacting with the first webpage;

identifying, at the server computer, based on the spoken words from the audio data representing the verbal response of the audience to the first message, a particular point in a conversation with the member of the audience; and

processing, at the server computer, the spoken words from the audio data representing the verbal response of the audience to the first message;

determining, at the server computer, a response to convey to the audience via the client device,

wherein the response to convey to the audience is determined based at least in part on the spoken words from the audio data representing the verbal response by the audience to the first message, and

converting, at the server computer, the response to convey to the audience to response audio data to be played to the audience;

wherein the response to convey to the member of the audience is presented on a second webpage different from the first webpage such that the response to convey to the member of the audience continues the conversational advertisement on the second webpage, picking up from the identified particular point in the conversation with the member of the audience such that the conversation with the member of the audience continues where the member of the audience left off from the at least two initial interactions with the conversational advertisement orchestrated through the first webpage.

10. The method of claim 9,

wherein the conversational advertisement includes an advertisement script,

wherein processing, at the server computer, the spoken words from the audio data representing the verbal response by the audience to the first message includes comparing, at the server computer, the spoken words from the audio data representing the verbal response by the audience to the first message to at least a portion of the advertisement script, and

wherein determining, at the server computer, the response to convey to the audience includes identifying, at the server computer, a script response that is included in the advertisement script.

11. The method of claim 10, wherein the received indication to present the advertisement is received, at the server computer, from an agent operating on the client device.

12. The method of claim 9, wherein identifying, at the server computer, a conversational advertisement to present to the audience includes identifying, at the server computer, a conversational advertisement associated with an input of the audience on the client device.

13. The method of claim 9, wherein:

determining, at the server computer, the response to convey to the audience is based at least in part on a previous response of the audience to one or more conversational advertisements, and

conveying, at the server computer, the first message of the conversational advertisement to the client device to be presented to the audience includes conveying, at the server computer, instructions to present the first message in both audio and textual forms on the client device.

14. The method of claim 9, further comprising determining, at the server computer, an action that is to be taken by the client device, wherein the action is determined based at least in part on the spoken words from the audio data representing the verbal response of the audience to the first message.

15. The method of claim 9, wherein the response to convey to the member of the audience is customized by incorporating details from a calendar entry into the response to convey to the member of the audience.

16. A non-transitory computer-readable medium whose contents, when executed by a computing system having a processor and a memory, cause the processor to perform a method of engaging an audience in a conversational advertisement, the method comprising:

identifying, at a server computer, a conversational advertisement to present to an audience via a client device in response to a received indication to present an advertisement,

wherein the conversational advertisement is selected from multiple conversational advertisements and

wherein the identified conversational advertisement provides a verbal interface such that the identified conversational advertisement provides response, to verbal input provided to the verbal interface, that are based on an identified meaning of the verbal input to the verbal interface;

orchestrating, through a first webpage, at least two initial interactions between the audience and the conversational advertisement, wherein one of the at least two initial interactions comprises;

conveying, at the server computer, a first message of the conversational advertisement to the client device to be presented to the audience; and

receiving, at the server computer, audio data from the client device representing a verbal response by the audience to the first message of the conversational advertisement,

wherein the audio data is received through the member of the audience interacting with the first webpage;

identifying, at the server computer, based on the spoken words from the audio data representing the verbal response of the audience to the first message, a particular point in a conversation with the member of the audience; and

processing, at the server computer, the spoken words from the audio data representing the verbal response of the audience to the first message;

determining, at the server computer, a response to convey to the audience via the client device,

wherein the response to convey to the audience is determined based at least in part on the spoken words from the audio data representing the verbal response by the audience to the first message, and

converting, at the server computer, the response to convey to the audience to response audio data to be played to the audience;

wherein the response to convey to the member of the audience is presented on a second webpage different from the first webpage such that the response to convey to the member of the audience continues the conversational advertisement on the second webpage, picking up from the identified particular point in the conversation with the member of the audience such that the conversation with the member of the audience continues where the member of the audience left off from the at least two initial interaction with the conversational advertisement orchestrated through the first webpage.

17. The non-transitory computer-readable medium of claim 16, wherein the conversational advertisement includes an advertisement script,

wherein processing, at the server computer, the spoken words from the audio data representing the verbal response by the audience to the first message includes comparing, at the server computer, the spoken words from the audio data representing the verbal response by the audience to the first message to at least a portion of the advertisement script, and

wherein determining, at the server computer, the response to convey to the audience includes identifying, at the server computer, a script response that is included in the advertisement script.

18. The non-transitory computer-readable medium of claim 17, wherein the received indication to present the advertisement is received, at the server computer, from an agent operating on the client device.

19. The non-transitory computer-readable medium of claim 16, wherein identifying, at the server computer, a conversational advertisement to present to the audience includes identifying, at the server computer, a conversational advertisement associated with an input of the audience on the client device.

20. The non-transitory computer-readable medium of claim 16, wherein:

determining, at the server computer, the response to convey to the audience is based at least in part on a previous response of the audience to one or more conversational advertisements, and

conveying, at the server computer, the first message of the conversational advertisement to the client device to be presented to the audience includes conveying, at the server computer, instructions to present the first message in both audio and textual forms on the client device.

21. The non-transitory computer-readable medium of claim 16, further comprising determining, at the server computer, an action that is to be taken by the client device, wherein the action is determined based at least in part on the spoken words from the audio data representing the verbal response of the audience to the first message.

22. The non-transitory computer-readable medium of claim 16,

wherein the response to convey to the member of the audience is customized by incorporating details from a calendar entry into the response to convey to the member of the audience.